© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1098
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .TXT
    -0.25
    aturdays
    -0.24
    âĦĹ
    -0.21
    .UIManager
    -0.21
    ç³ĸå°¿
    -0.21
     élè
    -0.20
    çļĦ姿æĢģ
    -0.20
    .appspot
    -0.20
    .sg
    -0.20
    stdafx
    -0.20
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.26
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.25
     //~
    0.25
     Noticed
    0.22
    娱ä¹IJå¹³åı°
    0.22
     fileprivate
    0.22
    对çŃĸ
    0.20
    ATEGORY
    0.20
    opcion
    0.19
     madrid
    0.19
    Activations Density 1.695%

    No Known Activations